© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45338
    Prev
    Next
    INDEX
    Explanations

    highway route contract length

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron specializes in detecting mentions of numbered roads or highways (e.g. "State Road 225," "NM 225," "Farm to Market Road 1905," etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glanced
    -1.01
    řev
    -0.85
     dataList
    -0.80
     newData
    -0.78
     takes
    -0.78
     vantaggi
    -0.77
     isEmpty
    -0.75
     незавер
    -0.72
    США
    -0.72
     Oliven
    -0.72
    POSITIVE LOGITS
     NHS
    0.91
    Route
    0.87
     Contract
    0.86
     contracts
    0.84
     BIEN
    0.83
     mostrando
    0.83
    various
    0.82
    Ht
    0.82
    contracts
    0.82
     Route
    0.82
    Activations Density 0.021%

    No Known Activations